arXiv research

New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.

We investigate multiarmed bandits with delayed feedback, where the delays need neither be identical nor bounded. We first prove that "delayed" Exp3 achieves the $O(\sqrt{(KT + D)\ln K} )$ regret bound conjectured by Cesa-Bianchi et al. [2019] in the case of variable, but bounded delays. Here, $K$ is the number of actio…

We propose a new algorithm for adversarial multi-armed bandits with unrestricted delays. The algorithm is based on a novel hybrid regularizer applied in the Follow the Regularized Leader (FTRL) framework. It achieves $\mathcal{O}(\sqrt{kn}+\sqrt{D\log(k)})$ regret guarantee, where $k$ is the number of arms, $n$ is the …

New algorithm tackles multi-armed bandit with arbitrary delays and general bounded losses.

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has been increasing interest in the construction of (and robustness to) unrestricted…

We study learning problems involving arbitrary classes of functions $F$, distributions $X$ and targets $Y$. Because proper learning procedures, i.e., procedures that are only allowed to select functions in $F$, tend to perform poorly unless the problem satisfies some additional structural property (e.g., that $F$ is co…

Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small…

Study of unrestricted virtual braid groups and their properties.

We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn stylistic and stochastic modifications leveraging state-of-the-art generative models. …

We consider the group of unrestricted virtual braids, describe its structure and explore its relations with fused links. Also, we define the groups of flat virtual braids and virtual Gauss braids and study some of their properties, in particular their linearity.

Generative models create indistinguishable adversarial objects for object detection.

This paper considers the optimal dividend payment problem in piecewise-deterministic compound Poisson risk models. The objective is to maximize the expected discounted dividend payout up to the time of ruin. We provide a comparative study in this general framework of both restricted and unrestricted payment schemes, wh…

New methods reduce extrapolation errors in feature importance.

Recently, it is proven that generalized Robertson-Walker space-times in all orthogonal subspaces of Gray's decomposition but one(unrestricted) are perfect fluid space-times. GRW space-times in the unrestricted subspace are identified by having constant scalar curvature. Generalized quasi-Einstein GRW space-times have a…

MoMA improves model-based RL by using unrestricted policy classes.

Study compares adaptive vs fixed query learning methods.

R. Kashaev and N. Reshetikhin introduced the notion of holonomy braiding extending V. Turaev's homotopy braiding to describe the behavior of cyclic representations of the unrestricted quantum group $U_qsl_2$ at root of unity. In this paper, using quandles and biquandles we develop a general theory for Reshetikhin-Turae…

New method optimizes policies without assuming known link functions between preferences and rewards.

The rebmix package provides R functions for random univariate and multivariate finite mixture model generation, estimation, clustering and classification. The paper is focused on multivariate normal mixture models with unrestricted variance-covariance matrices. The objective is to show how to generate datasets for a kn…

Develops a stochastic approach to financial market delays.

Paper tackles action delays in reinforcement learning, proposing a delay-aware framework.

New algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.

Banker-OMD improves online learning with delayed feedback.

New algorithm handles delayed feedback robustly, reducing regret without knowing delay bounds.

Paper tackles delays in multi-agent reinforcement learning, improving performance.

Study on synchronization in financial markets with time delays.

New algorithm tackles stochastic bandits with varying arm-dependent delays.

BayTiDe discovers time-delayed differential equations from noisy data.

TSMB handles time delays in multivariate time series data.

New algorithm reduces regret in delayed feedback generalised linear bandits.

Adapts Exp3 to adversarial bandits with delays and data.

Capacity-Constrained Online Convex Optimization with Delayed Feedback

New algorithm tackles non-stationary delayed feedback in recommender systems.

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

Predicting conversion rates (CVRs) in display advertising (e.g., predicting the proportion of users who purchase an item (i.e., a conversion) after its corresponding ad is clicked) is important when measuring the effects of ads shown to users and to understanding the interests of the users. There is generally a time de…

We study a variant of the stochastic $K$-armed bandit problem, which we call "bandits with delayed, aggregated anonymous feedback". In this problem, when the player pulls an arm, a reward is generated, however it is not immediately observed. Instead, at the end of each round the player observes only the sum of a number…

Study online learning with delays and capacity constraints, achieving optimal regret bounds.

Online learning with delayed feedback has received increasing attention recently due to its several applications in distributed, web-based learning problems. In this paper we provide a systematic study of the topic, and analyze the effect of delay on the regret of online learning algorithms. Somewhat surprisingly, it t…

Federated learning technique improves convergence speed with communication delays.

Study a dual risk model with innovation delays, focusing on ruin probability and time.

Study on unimodality of plucking polynomial with delay function.

Recent work has shown that topological enhancements to recurrent neural networks (RNNs) can increase their expressiveness and representational capacity. Two popular enhancements are stacked RNNs, which increases the capacity for learning non-linear functions, and bidirectional processing, which exploits acausal informa…

New algorithms reduce forecasting errors by leveraging optimistic learning and hinting.

We provide tight finite-time convergence bounds for gradient descent and stochastic gradient descent on quadratic functions, when the gradients are delayed and reflect iterates from $τ$ rounds ago. First, we show that without stochastic noise, delays strongly affect the attainable optimization error: In fact, the error…

A stochastic model helps maintain insufficiently funded pension funds.

We propose a model to study the effects of delayed information on option pricing. We first talk about the absence of arbitrage in our model, and then discuss super replication with delayed information in a binomial model, notably, we present a closed form formula for the price of convex contingent claims. Also, we addr…

A new algorithm tackles delayed combinatorial semi-bandit with causal relations.

Stochastic delay differential equations (SDDE's) have been used for financial modeling. In this article, we study a SDDE obtained by the equation of a CIR process, with an additional fixed delay term in drift; in particular, we prove that there exists a unique strong solution (positive and integrable) which we call fix…